© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3920
    Prev
    Next
    INDEX
    Explanations

    descriptions of characters in a story or film

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    394
    +0.09
    0.3%
    872
    +0.09
    0.3%
    227
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.09
    0.05
    1879
    +0.09
    0.04
    1181
    +0.09
    0.05
    Negative Logits
     makro
    -1.30
     akut
    -1.21
     kram
    -1.12
     panik
    -1.10
     optik
    -1.09
     zoll
    -1.07
     silikon
    -1.05
     vertik
    -1.04
     kac
    -1.03
     protokol
    -1.02
    POSITIVE LOGITS
     character
    0.73
     portrayed
    0.72
     amigurumi
    0.68
     portrayal
    0.67
     portray
    0.66
     characters
    0.66
     personnage
    0.65
     fles
    0.64
     believable
    0.63
     personagem
    0.60
    Activations Density 0.641%

    No Known Activations